diff_of_means ratio_of_sd monthly_amplitude_ratio_of_means sign_correlation qqplot_mae acf_mae extremogram_mae
xgboost.mri_esm2_0.ssp370 -0.59% 0.947 0.876 0.499 5.404 0.059 0.036
lstm.cesm2.ssp585 1.76% 0.946 0.876 0.512 6.429 0.042 0.044
xgboost.mri_esm2_0.ssp434 -2.07% 0.952 0.863 0.510 5.870 0.077 0.032
lstm.mri_esm2_0.ssp245 2.08% 0.933 0.849 0.521 5.850 0.083 0.035
nv.cesm2.ssp245 2.27% 0.916 0.907 0.521 8.147 0.044 0.040
nv.cesm2.ssp585 2.47% 0.920 0.951 0.521 7.376 0.037 0.036
lstm.cesm2.ssp370 2.74% 0.937 0.875 0.504 7.753 0.033 0.040
lstm.cesm2.ssp245 2.90% 0.939 0.873 0.521 8.400 0.035 0.033
lstm.mri_esm2_0.ssp434 3.23% 0.930 0.865 0.517 7.704 0.074 0.036
nv.cesm2.ssp370 3.38% 0.911 0.923 0.502 8.558 0.038 0.044
xgboost.mri_esm2_0.ssp245 -3.44% 0.955 0.851 0.512 8.475 0.085 0.041
lstm.mri_esm2_0.ssp370 3.48% 0.930 0.877 0.498 7.791 0.053 0.034
lstm.ec_earth3.ssp434 4.14% 0.923 0.909 0.493 8.679 0.011 0.034
nv.mri_esm2_0.ssp370 -4.53% 1.000 0.916 0.495 10.364 0.111 0.033
xgboost.cesm2.ssp245 5.04% 0.904 0.879 0.511 12.096 0.018 0.032
xgboost.cesm2.ssp585 5.41% 0.894 0.871 0.512 12.372 0.021 0.037
nv.mri_esm2_0.ssp434 -5.80% 0.995 0.903 0.516 12.612 0.124 0.034
xgboost.cesm2.ssp370 6.18% 0.892 0.860 0.507 13.902 0.019 0.035
nv.mri_esm2_0.ssp245 -7.08% 0.993 0.873 0.513 14.921 0.129 0.036
nv.ec_earth3.ssp434 7.28% 0.869 0.891 0.498 14.905 0.047 0.051
cnn.mri_esm2_0.ssp245 8.42% 0.872 0.861 0.507 17.291 0.065 0.044
cnn.cesm2.ssp585 8.61% 0.865 0.914 0.518 18.275 0.015 0.034
cnn.cesm2.ssp370 8.95% 0.864 0.902 0.498 18.848 0.016 0.037
cnn.cesm2.ssp245 9.11% 0.875 0.917 0.504 19.021 0.017 0.047
cnn.mri_esm2_0.ssp434 9.27% 0.862 0.894 0.524 18.939 0.051 0.033
cnn.ec_earth3.ssp434 9.40% 0.867 0.955 0.488 18.717 0.036 0.047
cnn.mri_esm2_0.ssp370 9.45% 0.869 0.914 0.499 18.890 0.023 0.034
xgboost.ec_earth3.ssp434 12.99% 0.878 0.874 0.498 25.849 0.016 0.037

Time series of the first days

Distribution of daily values by month

QQ Plot

Distribution of the undownscaled value on days with estimated extremes values.

On the x-axis we have the daily mean (standardized). It says Undownscaled value, but is the daily mean after the downscaling. A good idea is to plot the original undownscaled value.

The purpose of this plot is to illustrate the distribution of P(undownscaled value | we predicted an extreme). This is useful because it reveals how much information we can recover concerning extreme events. If the distribution is skewed to the right, it suggests that we’re predicting extreme values only when extreme values have already occurred. Conversely, if the lower tail of the distribution resembles the reanalysis data, it indicates that we can capture short-duration extremes (e.g., brief periods of heavy rainfall, such as an intense downpour lasting an hour before stopping).

Autocorrelogram

Extremogram